{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:24:39Z","timestamp":1781285079433,"version":"3.54.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030983574","type":"print"},{"value":"9783030983581","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98358-1_42","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:06:56Z","timestamp":1647259616000},"page":"533-543","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Time-Frequency Attention for Speech Emotion Recognition with Squeeze-and-Excitation Blocks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5765-2128","authenticated-orcid":false,"given":"Ke","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8849-8389","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6326-903X","authenticated-orcid":false,"given":"Jiayue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0706-2103","authenticated-orcid":false,"given":"Jun","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Bhosale, S., Chakraborty, R., Kopparapu, S.K.: Deep encoded linguistic and acoustic cues for attention based end to end speech emotion recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7189\u20137193 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054621"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: Iemocap: interactive emotional dyadic motion capture database. In: Language Resources and Evaluation vol. 42, pp. 335\u2013359 (2008)","DOI":"10.1007\/s10579-008-9076-6"},{"issue":"10","key":"42_CR3","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/LSP.2018.2860246","volume":"25","author":"M Chen","year":"2018","unstructured":"Chen, M., He, X., Yang, J., Zhang, H.: 3-D convolutional recurrent neural networks with attention model for speech emotion recognition. IEEE Sig. Process. Lett. 25(10), 1440\u20131444 (2018)","journal-title":"IEEE Sig. Process. Lett."},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Ebrahimpour, M.K., et al.: Ventral-dorsal neural networks: object detection via selective attention. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 986\u2013994 (2019)","DOI":"10.1109\/WACV.2019.00110"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Guizzo, E., Weyde, T., Leveson, J.B.: Multi-time-scale convolution for emotion recognition from speech audio signals. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6489\u20136493 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053727"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: INTERSPEECH, pp. 223\u2013227 (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"6","key":"42_CR8","first-page":"154","volume":"8","author":"SM Jagdale","year":"2016","unstructured":"Jagdale, S.M.: Speech emotion recognition with low level and prosodic features: a review. Digit. Sig. Process. 8(6), 154\u2013158 (2016)","journal-title":"Digit. Sig. Process."},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Kim, J., Saurous, R.A.: Emotion recognition from human speech using temporal information and deep learning. In: Interspeech 2018, pp. 937\u2013940 (2018)","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: INTERSPEECH, pp. 1537\u20131540 (2015)","DOI":"10.21437\/Interspeech.2015-336"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Li, P., Song, Y., McLoughlin, I.V., Guo, W., Dai, L.: An attention pooling based representation learning method for speech emotion recognition. In: Interspeech 2018, pp. 3087\u20133091 (2018)","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"42_CR12","unstructured":"Li, Z.: A study on emotional feature analysis and recognition in speech signal. J. China Inst. Commun. (2000)"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wang, L., Guo, L., Dang, J.: Speech emotion recognition with local-global aware deep representation learning. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7174\u20137178 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053192"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Luengo, I., Navas, E., Hernaez, I.: Automatic emotion recognition using prosodic parameters. In: INTERSPEECH, pp. 493\u2013496 (2005)","DOI":"10.21437\/Interspeech.2005-324"},{"key":"42_CR15","unstructured":"Montero, J., Guti\u00e9rrez-Arriola, J., Col\u00e1s, J.: Analysis and modelling of emotional speech in Spanish (1999)"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Muppidi, A., Radfar, M.: Speech emotion recognition using quaternion convolutional neural networks. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6309\u20136313 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414248"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Nediyanchath, A., Paramasivam, P., Yenigalla, P.: Multi-head attention for speech emotion recognition with auxiliary learning of gender recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7179\u20137183 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"42_CR18","unstructured":"Petrushin, V.A.: Emotion in speech: Recognition and application to call centers (1999)"},{"issue":"3","key":"42_CR19","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/S0167-6393(02)00049-3","volume":"39","author":"M Slaney","year":"2003","unstructured":"Slaney, M., McRoberts, G.: Baby ears: a recognition system for affective vocalizations. Speech Commun. 39(3), 367\u2013384 (2003)","journal-title":"Speech Commun."},{"key":"42_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems vol. 30, pp. 5998\u20136008 (2017)"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., Xue, M., Culhane, R., Diao, E., Ding, J., Tarokh, V.: Speech emotion recognition with dual-sequence LSTM architecture. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6474\u20136478 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Speech emotion recognition using capsule networks. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6695\u20136699 (2019)","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, F., Cui, X., Zhang, W.: Speech emotion recognition with multiscale area attention and data augmentation. arXiv preprint arXiv:2102.01813 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414635"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Y., Xu, H., Zou, J.: HGFM : A hierarchical grained and feature model for acoustic emotion recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6499\u20136503 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053039"},{"key":"42_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/978-3-030-37731-1_53","volume-title":"MultiMedia modeling","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Shi, Z., Han, J., Shi, A., Ma, D.: FurcaNeXt: end-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11961, pp. 653\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37731-1_53"},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Du, J., Wang, Z., Zhang, J., Tu, Y.: Attention based fully convolutional network for speech emotion recognition. In: 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1771\u20131775 (2018)","DOI":"10.23919\/APSIPA.2018.8659587"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98358-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T10:15:28Z","timestamp":1708337728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98358-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983574","9783030983581"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98358-1_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phu Quoc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"84","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}